© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17133
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEX
    -0.06
    iene
    -0.06
    oline
    -0.06
    iddy
    -0.06
     uitg
    -0.06
    lex
    -0.06
    aurus
    -0.06
    tering
    -0.06
    ½ij
    -0.06
    [[
    -0.06
    POSITIVE LOGITS
    esas
    0.08
    èn
    0.08
    bauer
    0.07
    stal
    0.07
    大麻
    0.07
    endam
    0.07
    èĪ¶
    0.07
    æĸĩçIJĨ
    0.07
    ä¸Ī
    0.07
    ä¹ĭæ°´
    0.07
    Activations Density 0.000%

    No Known Activations